Emptiness criterion for the Mahalanobis shell of shifted Gaussians
OpenStatUnlearn.shiftedGaussianShell_empty_iffFor shifted Gaussians on with common positive definite covariance , and levels , the set
of parameters whose two Mahalanobis distances from and satisfy the level conditions is empty if and only if
i.e. exactly when the preservation ball around cannot reach past the removal ball around .For these are Mahalanobis balls; the criterion is invariant under the change of coordinates that turns them into Euclidean ones, which is the sense in which the paper's Euclidean picture applies.
Retired. Retired: as stated (without a dimension hypothesis) this is false at d = 0, where the ambient space is a single point and the Mahalanobis distance vanishes identically: with α = ε = 1 the shell is empty although Δ + ε < α fails. The corrected statement, with the necessary hypothesis d ≥ 1, is StatUnlearn.shiftedGaussianShell_empty_iff_posDim.
import Mathlib.Probability.Distributions.Gaussian.Multivariate import Mathlib.Probability.Distributions.Gaussian.Real import Mathlib.Analysis.InnerProductSpace.EuclideanDist open MeasureTheory ProbabilityTheory
namespace StatUnlearn
theorem shiftedGaussianShell_empty_iff {d : ℕ} (S : Matrix (Fin d) (Fin d) ℝ) (hS : S.PosDef)
(μ₁ ν₁ : EuclideanSpace ℝ (Fin d)) (α ε : ℝ) (hα : 0 ≤ α) (hε : 0 ≤ ε) :
({μ : EuclideanSpace ℝ (Fin d) |
α ≤ Real.sqrt (inner ℝ (μ₁ - μ) (Matrix.toEuclideanLin S⁻¹ (μ₁ - μ))) ∧
Real.sqrt (inner ℝ (ν₁ - μ) (Matrix.toEuclideanLin S⁻¹ (ν₁ - μ))) ≤ ε}
: Set (EuclideanSpace ℝ (Fin d))) = ∅
↔ Real.sqrt (inner ℝ (μ₁ - ν₁) (Matrix.toEuclideanLin S⁻¹ (μ₁ - ν₁))) + ε < α := by
sorry
end StatUnlearn